MLP-from-scratch

I tried to implement Multilayer Perceptron without any framework like Keras or similar ones.
The data was fashion mnist, Fashion-MNIST is a dataset of Zalando's article images—consisting of a training set of 60,000 examples and a test set of 10,000 examples.
Different activation fuctions such as linear, softmax, relu, tanh was tested and the suitable one can be chosen based on the data.
For optimiser i implemented SGD, Momentum_SGD, Adagrad, RMSprop, Adam.